← Back to Skills Marketplace
OpenClaw DX
by
Austin S. Lin
· GitHub ↗
· v1.9.0
· MIT-0
563
Downloads
0
Stars
4
Active Installs
10
Versions
Install in OpenClaw
/install openclaw-dx
Description
Diagnose and fix openclaw gateway issues. Use when the gateway is stuck, not starting, crash-looping, or rejecting connections. Covers main and --profile ves...
Usage Guidance
This skill appears to be a legitimate diagnostic playbook, but it reads sensitive local files and an environment variable that are not declared in the registry metadata. Before installing or allowing autonomous use: 1) Confirm you trust the skill's source (owner ID is present but no homepage). 2) Backup ~/.openclaw and related files. 3) Ask the publisher to explicitly declare OPENCLAW_GATEWAY_TOKEN and any credential files the skill reads. 4) If you plan to let the agent run autonomously, ensure outputs (logs, tokens) won't be transmitted off-host; consider running the steps manually or in a controlled environment first. 5) Request clarification or an explicit command that writes the incident report to ~/clawd/inbox (or remove the claim) so the behavior is transparent.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-dx
Version: 1.9.0
The skill bundle provides extensive diagnostic and repair tools for the OpenClaw gateway, but it requires high-risk permissions. It explicitly instructs the agent to read sensitive authentication tokens from 'auth-profiles.json' and access the 'OPENCLAW_GATEWAY_PASSWORD' environment variable in 'SKILL.md'. While these actions are aligned with the stated purpose of troubleshooting, the broad access to credentials and the ability to manipulate system services via 'launchctl' and 'kill' represent a significant security risk.
Capability Assessment
Purpose & Capability
The skill's name/description (gateway diagnosis & remediation) matches the commands and fixes in SKILL.md (log tails, lsof/ps, openclaw CLI, config edits). Minor inconsistency: the header claims it 'writes incident report to ~/clawd/inbox' but the provided runtime instructions do not show any explicit commands that create or write that report.
Instruction Scope
Instructions direct the agent/operator to read multiple user config and credential files (~/.openclaw/*, ~/.openclaw-vesper/*), tail logs, inspect auth-profiles.json (tokens/expiry), and echo the OPENCLAW_GATEWAY_TOKEN env var. Those operations are functionally appropriate for debugging but are sensitive and are not explicitly limited (e.g., no guidance on redaction or safe handling). The instructions also include editing configs and running interactive re-auth — normal for troubleshooting but high-sensitivity actions.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk or fetched during install, which reduces technical risk.
Credentials
Metadata declares no required env vars or credentials, yet the instructions explicitly read OPENCLAW_GATEWAY_TOKEN and local auth-profiles.json (which contain access tokens/refresh tokens). The skill therefore accesses sensitive secrets without declaring them in requires.env/primaryEnv; this discrepancy should be justified or corrected.
Persistence & Privilege
always is false and there are no install-time changes or claims to modify other skills or global agent settings. The skill asks the operator to edit local config files as part of remediation, which is expected for this purpose.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-dx - After installation, invoke the skill by name or use
/openclaw-dx - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.9.0
Failure mode #19: auto-update kills all gateways simultaneously. Updated triage protocol with session bloat checks. Post-upgrade checklist now includes plist regeneration.
v1.7.0
Add compaction model timeout (#17), qmd embed debugging notes
v1.5.1
openclaw-dx 1.5.1
- No file changes detected in this version.
- Skill functionality, documentation, and triage protocol remain unchanged from the previous release.
v1.5.0
Genericize agent references, strengthen config.patch batching prevention guidance, clarify token auth remote.token requirement applies to any profile using token mode
v1.4.0
Profile-aware diagnostics (Main vs Vesper paths), auth token expiry checking, add unconfigured fallback provider failure mode, add Google/Gemini common sub-failure
v1.3.1
Add failure modes: invalid JSON from hand-edits, missing gateway.remote.token for token auth
v1.3.0
Add failure modes #10 (invalid JSON from hand-edits) and #11 (missing gateway.remote.token for token auth CLI/TUI connectivity)
v1.2.0
Scrub plaintext passwords (use $OPENCLAW_GATEWAY_PASSWORD env var), update shell config refs to ~/.zshrc, add Node heap tuning section, add memory threshold cross-ref, add new troubleshooting sections (failover cascade, plugin configSchema)
v1.1.0
Expanded: added common failure modes (token expiry, config wipe, stale locks, device token mismatch, memory bloat, invalid plugins, port conflicts), memory thresholds table, post-upgrade checklist, incident report template
v1.0.0
Initial publish: triage protocol, failover cascade diagnosis, auth-profiles.json location, QMD/memory status, LaunchAgent restart table, incident report generation
Metadata
Frequently Asked Questions
What is OpenClaw DX?
Diagnose and fix openclaw gateway issues. Use when the gateway is stuck, not starting, crash-looping, or rejecting connections. Covers main and --profile ves... It is an AI Agent Skill for Claude Code / OpenClaw, with 563 downloads so far.
How do I install OpenClaw DX?
Run "/install openclaw-dx" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is OpenClaw DX free?
Yes, OpenClaw DX is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does OpenClaw DX support?
OpenClaw DX is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created OpenClaw DX?
It is built and maintained by Austin S. Lin (@siraustin); the current version is v1.9.0.
More Skills